VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI
The VASARI MRI feature set is a quantitative system designed to standardise glioma imaging descriptions. Though effective, deriving VASARI is time-consuming and seldom used clinically. We sought to resolve this problem with software automation and machine learning. Using glioma data from 1172 patien...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | NeuroImage: Clinical |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158224001074 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850266095442722816 |
|---|---|
| author | James K. Ruffle Samia Mohinta Kelly Pegoretti Baruteau Rebekah Rajiah Faith Lee Sebastian Brandner Parashkev Nachev Harpreet Hyare |
| author_facet | James K. Ruffle Samia Mohinta Kelly Pegoretti Baruteau Rebekah Rajiah Faith Lee Sebastian Brandner Parashkev Nachev Harpreet Hyare |
| author_sort | James K. Ruffle |
| collection | DOAJ |
| description | The VASARI MRI feature set is a quantitative system designed to standardise glioma imaging descriptions. Though effective, deriving VASARI is time-consuming and seldom used clinically. We sought to resolve this problem with software automation and machine learning. Using glioma data from 1172 patients, we developed VASARI-auto, an automated labelling software applied to open-source lesion masks and an openly available tumour segmentation model. Consultant neuroradiologists independently quantified VASARI features in 100 held-out glioblastoma cases. We quantified 1) agreement across neuroradiologists and VASARI-auto, 2) software equity, 3) an economic workforce analysis, and 4) fidelity in predicting survival. Tumour segmentation was compatible with the current state of the art and equally performant regardless of age or sex. A modest inter-rater variability between in-house neuroradiologists was comparable to between neuroradiologists and VASARI-auto, with far higher agreement between VASARI-auto methods. The time for neuroradiologists to derive VASARI was substantially higher than VASARI-auto (mean time per case 317 vs. 3 s). A UK hospital workforce analysis forecast that three years of VASARI featurisation would demand 29,777 consultant neuroradiologist workforce hours and >£1.5 ($1.9) million, reducible to 332 hours of computing time (and £146 of power) with VASARI-auto. The best-performing survival model utilised VASARI-auto features instead of those derived by neuroradiologists. VASARI-auto is a highly efficient and equitable automated labelling system, a favourable economic profile if used as a decision support tool, and non-inferior survival prediction. Future work should iterate upon and integrate such tools to enhance patient care. |
| format | Article |
| id | doaj-art-6886dfd3f17f40969518185269c6830e |
| institution | OA Journals |
| issn | 2213-1582 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj-art-6886dfd3f17f40969518185269c6830e2025-08-20T01:54:15ZengElsevierNeuroImage: Clinical2213-15822024-01-014410366810.1016/j.nicl.2024.103668VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRIJames K. Ruffle0Samia Mohinta1Kelly Pegoretti Baruteau2Rebekah Rajiah3Faith Lee4Sebastian Brandner5Parashkev Nachev6Harpreet Hyare7Queen Square Institute of Neurology, University College London, London, UK; Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, London, UK; Corresponding author at: Institute of Neurology, UCL, London WC1N 3BG, UK.Queen Square Institute of Neurology, University College London, London, UKLysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, London, UKQueen Square Institute of Neurology, University College London, London, UKQueen Square Institute of Neurology, University College London, London, UKDivision of Neuropathology and Department of Neurodegenerative Disease, Queen Square Institute of Neurology, University College London, London, UKQueen Square Institute of Neurology, University College London, London, UKQueen Square Institute of Neurology, University College London, London, UK; Lysholm Department of Neuroradiology, National Hospital for Neurology and Neurosurgery, London, UKThe VASARI MRI feature set is a quantitative system designed to standardise glioma imaging descriptions. Though effective, deriving VASARI is time-consuming and seldom used clinically. We sought to resolve this problem with software automation and machine learning. Using glioma data from 1172 patients, we developed VASARI-auto, an automated labelling software applied to open-source lesion masks and an openly available tumour segmentation model. Consultant neuroradiologists independently quantified VASARI features in 100 held-out glioblastoma cases. We quantified 1) agreement across neuroradiologists and VASARI-auto, 2) software equity, 3) an economic workforce analysis, and 4) fidelity in predicting survival. Tumour segmentation was compatible with the current state of the art and equally performant regardless of age or sex. A modest inter-rater variability between in-house neuroradiologists was comparable to between neuroradiologists and VASARI-auto, with far higher agreement between VASARI-auto methods. The time for neuroradiologists to derive VASARI was substantially higher than VASARI-auto (mean time per case 317 vs. 3 s). A UK hospital workforce analysis forecast that three years of VASARI featurisation would demand 29,777 consultant neuroradiologist workforce hours and >£1.5 ($1.9) million, reducible to 332 hours of computing time (and £146 of power) with VASARI-auto. The best-performing survival model utilised VASARI-auto features instead of those derived by neuroradiologists. VASARI-auto is a highly efficient and equitable automated labelling system, a favourable economic profile if used as a decision support tool, and non-inferior survival prediction. Future work should iterate upon and integrate such tools to enhance patient care.http://www.sciencedirect.com/science/article/pii/S2213158224001074GliomaDeep learningArtificial intelligenceVASARIDecision supportRadiology |
| spellingShingle | James K. Ruffle Samia Mohinta Kelly Pegoretti Baruteau Rebekah Rajiah Faith Lee Sebastian Brandner Parashkev Nachev Harpreet Hyare VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI NeuroImage: Clinical Glioma Deep learning Artificial intelligence VASARI Decision support Radiology |
| title | VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI |
| title_full | VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI |
| title_fullStr | VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI |
| title_full_unstemmed | VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI |
| title_short | VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI |
| title_sort | vasari auto equitable efficient and economical featurisation of glioma mri |
| topic | Glioma Deep learning Artificial intelligence VASARI Decision support Radiology |
| url | http://www.sciencedirect.com/science/article/pii/S2213158224001074 |
| work_keys_str_mv | AT jameskruffle vasariautoequitableefficientandeconomicalfeaturisationofgliomamri AT samiamohinta vasariautoequitableefficientandeconomicalfeaturisationofgliomamri AT kellypegorettibaruteau vasariautoequitableefficientandeconomicalfeaturisationofgliomamri AT rebekahrajiah vasariautoequitableefficientandeconomicalfeaturisationofgliomamri AT faithlee vasariautoequitableefficientandeconomicalfeaturisationofgliomamri AT sebastianbrandner vasariautoequitableefficientandeconomicalfeaturisationofgliomamri AT parashkevnachev vasariautoequitableefficientandeconomicalfeaturisationofgliomamri AT harpreethyare vasariautoequitableefficientandeconomicalfeaturisationofgliomamri |